Gemini 3.5 Flash vs Gemini 3.6 Flash

Wins 1 of 15 benchmarks
$1.60 / task
Wins 6 of 15 benchmarks
Different efforts: medium · high · Compare all at high
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation
Gemini 3.5 Flash · high42.1
Gemini 3.6 Flash53
GDPval-AA (work tasks) 2.1 GDPval-AA (work tasks) 2.1: Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work
Gemini 3.5 Flash · high35.1
Gemini 3.6 Flash39.2
τ³-Banking · AA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows
Gemini 3.5 Flash · high32.2
Gemini 3.6 Flash29.9
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Gemini 3.5 Flash · high6.6
Gemini 3.6 Flash7.1
AA-Briefcase 1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating
Gemini 3.5 Flash876.8
Gemini 3.6 Flash953.9
AA-LCR (long context) 1.1 AA-LCR (long context) 1.1: Questions that need reading and connecting facts across very long documents (around 100K tokens)
Gemini 3.5 Flash74.3
Gemini 3.6 Flash80
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Gemini 3.5 Flash · high36.1
Gemini 3.6 Flash46.7
Toolathlon-Verified Toolathlon-Verified: Toolathlon-Verified as reported in this launch evaluation; the post is the authority for the recorded task and grading scope
Gemini 3.5 Flash · high67.3
Gemini 3.6 Flash—
AA Analyst Agent AA Analyst Agent: Data-analyst tasks: the model explores data with tools and reports findings
Gemini 3.5 Flash · high45
Gemini 3.6 Flash—
ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer
Gemini 3.5 Flash · high40.3
Gemini 3.6 Flash—
APEX-Agents APEX-Agents: Agents complete long-horizon professional-services tasks across realistic applications
Gemini 3.5 Flash · high47.1
Gemini 3.6 Flash—
Terminal-Bench Hard (version unstated) Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal
Gemini 3.5 Flash39.4
Gemini 3.6 Flash—
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success
Gemini 3.5 Flash · high50.1
Gemini 3.6 Flash—
EBR Bench EBR Bench: Agents learn to play Earthborne Rangers across repeated playthroughs
Gemini 3.5 Flash · high4.8
Gemini 3.6 Flash—
Furniture Assembly Furniture Assembly: Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step
Gemini 3.5 Flash—
Gemini 3.6 Flash23.3

Specs

SpecGemini 3.5 FlashGemini 3.6 Flash
Input, per 1M$1.50!$0.75
Output, per 1M$9!$3.75
Cost per task?—$1.60
Speed, tok/s199209
Context1M1M
WeightsClosedClosed
ReleasedMay 2026Jul 2026
See images✓✓
Read PDFsPartial✓
Hear audio✓✓
Watch video✓✓
Call tools✓✓
Force a tool callPartialPartial
Return strict JSON✓✓
Search the web?✓
Run code?✓
Use a computer?Partial

What breaks when you switch

Gemini 3.5 Flash → Gemini 3.6 Flash
Nothing known.
Gemini 3.6 Flash → Gemini 3.5 Flash
Nothing known.